head	1.3;
access;
symbols
	pkgsrc-2021Q3:1.2.0.4
	pkgsrc-2021Q3-base:1.2
	pkgsrc-2021Q2:1.2.0.2
	pkgsrc-2021Q2-base:1.2;
locks; strict;
comment	@# @;


1.3
date	2021.11.20.20.05.37;	author wiz;	state dead;
branches;
next	1.2;
commitid	cqHofXrii3T3wzhD;

1.2
date	2021.06.10.12.26.26;	author nia;	state Exp;
branches;
next	1.1;
commitid	XmFXI7JIS6eddAWC;

1.1
date	2021.06.10.09.57.40;	author nia;	state Exp;
branches;
next	;
commitid	gXxG4IZE4LNfozWC;


desc
@@


1.3
log
@pocl: update to 1.8.

Notable User Facing Changes
---------------------------

- support for LLVM 13
- CMake: Inter-Procedural Optimization is enabled on code of runtime library
  (libpocl.so is compiled with -flto on systems that support it).
- LTTng tracing improved - more command types are traced, and also
  some synchronous API calls (like clCreateBuffer) are traced.
- poclcc, tests and examples can be disabled with CMake options
- Valgrind support improved by making Valgrind aware of pocl's
  reference counting of cl_* objects
- kernels which are called by kernels are now force-inlined
- Support for NetBSD.
- Support for Unix systems without libdl.
- PoCL can now (optionally) respond to SIGUSR2 by printing
  some live debug information.
- improved SPIR support for CUDA devices

Notable Bug Fixes
-----------------

- Fixed a potential crash on Unix systems without sysfs mounted.
- Fixed compilation errors when building on macOS.
  - Fixed POCL_FAST_INIT macro; POCL_INIT_LOCK must be invoked with only one argument.
  - Fix bin/poclcc to not depend on OpenCL 2.0 symbols
- Fixed miscompilation in kernel loops with multiple conditionals with barriers in them.

Other
-----
- Add cmake options PARALLEL_COMPILE_JOBS, PARALLEL_LINK_JOBS to
  use ninja's seperate compile and link job pools.

- Improve memory architecture, buffer migration and allocation.
  Buffers are now allocated on a device when first used
  (previously each buffer was allocated on every device in context).

- the single global LLVMContext was replaced with
  multiple LLVMContexts, one per OpenCL cl_context.
  OpenCL code can now be compiled in parallel
  when using separate cl_contexts. This feature
  is disabled by default since it significantly slowed
  down PyOpenCL. This should be resolved by separating
  LLVM compilation in their own threads in the future.

- a new OpenCL extension was added to PoCL: cl_pocl_content_size.
  The extension allows the user to give optimization hint to PoCL,
  which will be used internally by PoCL to optimize buffer transfers
  between multiple devices.
@
text
@$NetBSD: patch-config.h.in.cmake,v 1.2 2021/06/10 12:26:26 nia Exp $

Fix detection of dlopen
https://github.com/pocl/pocl/pull/950

--- config.h.in.cmake.orig	2021-05-19 08:12:19.000000000 +0000
+++ config.h.in.cmake
@@@@ -35,6 +35,8 @@@@
 
 #cmakedefine ENABLE_SPIRV
 
+#cmakedefine HAVE_DLFCN_H
+
 #cmakedefine HAVE_FORK
 
 #cmakedefine HAVE_VFORK
@@@@ -57,8 +59,6 @@@@
 
 #cmakedefine HAVE_LTTNG_UST
 
-#cmakedefine HAVE_LIBDL
-
 #cmakedefine HAVE_OCL_ICD
 
 #cmakedefine HAVE_POSIX_MEMALIGN
@


1.2
log
@pocl: add links to upstream pull requests for patches

cpuinfo: check for fopen() failure when opening sysfs nodes to avoid segfault
https://github.com/pocl/pocl/pull/948

pocl_timing: fix detection of Unix monotonic clocks
https://github.com/pocl/pocl/pull/949

Fix detection of dlopen()/libdl
https://github.com/pocl/pocl/pull/950
@
text
@d1 1
a1 1
$NetBSD: patch-config.h.in.cmake,v 1.1 2021/06/10 09:57:40 nia Exp $
@


1.1
log
@add parallel/pocl

OpenCL (Open Computing Language) is an open, royalty-free standard for
cross-platform, parallel programming of diverse accelerators found in
supercomputers, cloud servers, personal computers, mobile devices and embedded
platforms.

PoCL is a portable open source (MIT-licensed) implementation of the OpenCL
standard (1.2 with some 2.0 features supported). In addition to being an easily
portable multi-device (truely heterogeneous) open-source OpenCL implementation,
a major goal of this project is improving interoperability of diversity of
OpenCL-capable devices by integrating them to a single centrally orchestrated
platform.
@
text
@d1 1
a1 1
$NetBSD$
d3 2
a4 1
dlfcn.h is a separate thing to libdl and should be detected separately.
@